/adr-plan
Analyze a task and produce an Architecture Decision Record with implementation steps.
$ npx -y skills add NikiforovAll/claude-code-rules --skill adr-plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/adr-plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Analyze a task and produce an Architecture Decision Record with implementation steps.
SKILL.md
adr-plan.SKILL.mdname: adr-plan
description: Analyze a task and produce an Architecture Decision Record with implementation steps.
allowed-tools: Agent, AskUserQuestion, Bash(npx adr *), Bash(git diff *), Bash(git log *), Bash(git status *), Bash(ls *), Bash(cat *), Read, Grep, Glob
ADR Plan: Task Analysis → Architecture Decision Record
Analyze a task, explore the codebase, and produce an ADR with concrete implementation steps.
Phase 1: Analyze
1. Read the task description, active plan, or task list 2. Explore affected areas of the codebase — do it concurrently for independent modules 3. Map blast radius — search for consumers of functions/types/routes being changed 4. Identify alternatives worth considering (at least 2)
Do this silently.
Phase 2: Detect ADR Setup
Check if the project has an ADR directory:
ls docs/adr/ || ls adr/ || ls doc/adr/
- **Found** → use existing directory, detect next number from existing files
- **Not found** → run `npx adr init en`, then proceed
Phase 3: Produce ADR Content
Write the ADR using `npx adr new "<title>"`, then edit the generated file with the following structure:
# ADR-NNNN: [Title]
## Status
Proposed
## Context
[What problem are we solving? What constraints exist?]
## Decision
[What we chose and why]
## Alternatives Considered
| Option | Pros | Cons |
|--------|------|------|
| ... | ... | ... |
## Implementation Steps
### Step 1: [Description]
- **Files:** [files to create/modify]
- **Depends on:** [previous step or "none"]
- **Done when:** [concrete acceptance criteria]
### Step 2: [Description]
...
## Consequences
- [Positive and negative outcomes, tradeoffs accepted]
Guidelines
- **Steps are ordered by dependency** — each step lists what it depends on
- **Steps are parallelizable when independent** — note which steps can run concurrently
- **Each step has concrete "done when" criteria** — no vague outcomes
- **Alternatives table is honest** — include the option you chose and why others lost
- Keep it short. 1-2 pages max. No padding.
Phase 4: Present to User
Show the ADR content and the file path. The user may:
- **Approve** → ADR stays as-is
- **Adjust** → edit and re-present
- **Cancel** → delete the file
Important
- The ADR is a planning artifact, not documentation for posterity
- Steps should map naturally to work units (a team member could own one or more steps)
- If the task is too simple for an ADR (single file, obvious fix), say so and skip
- Do not write implementation code — this is planning only
Read more
name: adr-plan description: Analyze a task and produce an Architecture Decision Record with implementation steps. allowed-tools: Agent, AskUserQuestion, Bash(npx adr *), Bash(git diff *), Bash(git log *), Bash(git status *), Bash(ls *), Bash(cat *), Read, Grep, Glob
ADR Plan: Task Analysis → Architecture Decision Record
Analyze a task, explore the codebase, and produce an ADR with concrete implementation steps.
Phase 1: Analyze
1. Read the task description, active plan, or task list 2. Explore affected areas of the codebase — do it concurrently for independent modules 3. Map blast radius — search for consumers of functions/types/routes being changed 4. Identify alternatives worth considering (at least 2)
Do this silently.
Phase 2: Detect ADR Setup
Check if the project has an ADR directory:
ls docs/adr/ || ls adr/ || ls doc/adr/
- **Found** → use existing directory, detect next number from existing files
- **Not found** → run `npx adr init en`, then proceed
Phase 3: Produce ADR Content
Write the ADR using `npx adr new "<title>"`, then edit the generated file with the following structure:
# ADR-NNNN: [Title] ## Status Proposed ## Context [What problem are we solving? What constraints exist?] ## Decision [What we chose and why] ## Alternatives Considered | Option | Pros | Cons | |--------|------|------| | ... | ... | ... | ## Implementation Steps ### Step 1: [Description] - **Files:** [files to create/modify] - **Depends on:** [previous step or "none"] - **Done when:** [concrete acceptance criteria] ### Step 2: [Description] ... ## Consequences - [Positive and negative outcomes, tradeoffs accepted]
Guidelines
- **Steps are ordered by dependency** — each step lists what it depends on
- **Steps are parallelizable when independent** — note which steps can run concurrently
- **Each step has concrete "done when" criteria** — no vague outcomes
- **Alternatives table is honest** — include the option you chose and why others lost
- Keep it short. 1-2 pages max. No padding.
Phase 4: Present to User
Show the ADR content and the file path. The user may:
- **Approve** → ADR stays as-is
- **Adjust** → edit and re-present
- **Cancel** → delete the file
Important
- The ADR is a planning artifact, not documentation for posterity
- Steps should map naturally to work units (a team member could own one or more steps)
- If the task is too simple for an ADR (single file, obvious fix), say so and skip
- Do not write implementation code — this is planning only
A collection of Claude Code recommendations and practices. Learn practical techniques to enhance your AI-assisted development workflow with Claude Code.
Other skills on claude-code-rules.
- /update-component-reference
This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.
Open skill - /version-bump
This skill automates version bumping during the release process for the Claude Code Handbook monorepo. It should be used when the user requests to bump versions, prepare a release, or increment version numbers across the repository.
Open skill - /spec-driven
Guide spec-driven development workflow (Requirements → Design → Tasks → Implementation) with approval gates between phases. Use when user wants structured feature planning or says "use spec-driven" or "follow the spec process".
Open skill - /subagent-review
Review changed code for reuse, quality, and efficiency using three parallel disposable subagents. This skill should be used when the user says "review", "simplify", "code review", or wants a one-shot code review without persistent reviewers.
Open skill - /team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to
Open skill - /handbook-discover
This skill should be used when users want to discover, browse, or audit cc-handbook marketplace plugins. Shows all available plugins with installation status, versions, and component breakdown (skills, agents, commands, MCP/LSP servers, hooks). Trigger phrases include "discover
Open skill

